DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
DropVLA is presented, an action-level backdoor attack that forces a reusable action primitive to execute at attacker-chosen decision points under a realistic pipeline-black-box setting with limited data-poisoning access, using a window-consistent relabeling scheme for chunked fine-tuning.
Zong-Huan Xu, Jiayu Li, Yun-Han Zhao et al.
· 5 citations